Skip to content
Back to the index

RunPeek

PyPIInfrastructure

PulseGate's liveness check found it on 11 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 11 Sep 2026. How this is checked

RunPeek is an open-source command-line observability tool for inspecting time, token usage, and costs in supported AI applications and Claude Code sessions. It runs locally and is intended for developers monitoring AI workflows.

Inferred · not functionally tested

Open SourceApache-2.0CLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Understanding where AI applications spend time and tokens, including associated usage costs.

Inferred · not functionally tested

Audience: AI developers and Claude Code users

Inferred · not functionally tested

Functions: analytics, monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

In the LLM & agent tracing space, RunPeek takes a focused approach. Inferred · not functionally tested: It focuses on understanding where AI applications spend time and tokens, including associated usage costs. Inferred · not functionally tested: It is built as an open-source project for AI developers and Claude Code users. Basis unknown · not verified: RunPeek is open source under the Apache-2.0 license. Basis unknown · not verified: RunPeek is available on the command line, and it can be self-hosted.

NemulAI builds and maintains RunPeek, and it first shipped in 2026. The project is developed in the open on GitHub with 15 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are time tracking, token tracking, and cost tracking.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Time tracking
  • Token tracking
  • Cost tracking
  • Local-first monitoring
  • Claude Code support
  • AI application observability

Topics: Inferred · not functionally tested

Tags
llm-observabilitytoken-usagecost-trackingclaude-codelocal-first
AI capabilities
TextStructured
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
openaimultiple
Written with
Claude Code
Runs on
CLISelf-hosted
Written with — evidence
Claude Code
commit ed36e57da717 · since Sep 2026

Trust & compliance

License
Apache-2.0
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed11 Sep · 00:23 UTC
    runpeek seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open

Frequently asked questions about RunPeek

What is RunPeek?
Inferred · not functionally tested: RunPeek focuses on understanding where AI applications spend time and tokens, including associated usage costs. It is catalogued under LLM & agent tracing on PulseGate.
Who should use RunPeek?
Inferred · not functionally tested: RunPeek is an open-source project built for AI developers and Claude Code users.
Does RunPeek have a free plan?
Basis unknown · not verified: Yes — RunPeek is open source under the Apache-2.0 license and free to use.
What platforms does RunPeek run on?
Basis unknown · not verified: RunPeek runs on the command line. It can also be self-hosted.
Is RunPeek still active?
PulseGate's liveness check found it on 11 Sep 2026. Its GitHub repository shows 15 commits in the last 90 days.
Who develops RunPeek?
RunPeek is developed by NemulAI.
When did RunPeek launch?
RunPeek first shipped in 2026.
Is RunPeek open source?
Basis unknown · not verified: Yes — RunPeek is open source under the Apache-2.0 license, developed on GitHub.

Similar projects

Closest matches by what these projects do